How to Use the Mercury MCP in Google ADK

Q: How do I register the Mercury toolset in Google ADK?

Run pip install google-adk and set up McpToolset with your Vinkius HTTP URL. Pass the toolset object directly to the tools list when initializing your Gemini LlmAgent to expose Mercury tools.

Q: What accounts can I inspect with this server?

The listaccounts and getaccount tools allow your Google ADK agent to view all your registered Mercury business banking accounts. You can inspect specific balances and account routing details on demand.

Feed live Mercury financial data directly into Google ADK pipelines for deep Gemini reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mercury MCP to Google ADK

Create your Vinkius account to connect Mercury to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Mercury with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-Context Financial Audits with Google ADK

The `list_transactions` tool feeds entire Mercury ledger histories directly into Gemini's million-token context window. This MCP Server lets your Google ADK agent process months of startup banking records in a single pass to identify complex spending patterns. Because the Mercury tool connects via Vinkius, your Google ADK agent pulls raw transaction rows directly into its working memory. You can run deep financial analysis without hitting context limits or truncating historical records.

Enterprise Invoicing on Google Cloud

The `list_invoices` tool retrieves Mercury account receivable records to match against enterprise data in BigQuery. Your Google ADK agent queries this endpoint to check outstanding customer payments against your database. You configure this by passing `McpToolset` with your Vinkius HTTP URL to your Google ADK `LlmAgent`. This joins live Mercury banking data with your existing Google Cloud infrastructure without complex ETL pipelines.

Restricted MCP Server Access

The `list_customers` tool lists your active Mercury invoicing clients for verification. Your Google ADK agent uses this tool to check client identities before running internal cloud workflows. The Google ADK allows you to use an optional `tool_names` filter to restrict what Mercury tools are exposed. This means you can lock down your agent to only see `list_customers` while blocking access to sensitive balance tools.

Setup guide

Set up Mercury MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Mercury tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Mercury_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Mercury tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Mercury. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Mercury now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Mercury MCP in Google ADK

Run `pip install google-adk` and set up `McpToolset` with your Vinkius HTTP URL. Pass the toolset object directly to the `tools` list when initializing your Gemini `LlmAgent` to expose Mercury tools.

Yes, your Google ADK agent can run a Gemini reasoning loop that pulls live bank records using `list_transactions` and queries BigQuery tables in the same step. This lets you compare real-time Mercury bank balances with your internal financial models.

Yes, the Google ADK framework supports both Stdio and HTTP transports to connect with the Vinkius MCP Server. Your Mercury banking tokens remain safe inside your Google Cloud environment, passing only through encrypted channels.

The `list_accounts` and `get_account` tools allow your Google ADK agent to view all your registered Mercury business banking accounts. You can inspect specific balances and account routing details on demand.

Your Mercury bank account details, balances, invoices, and card lists are processed inside secure V8 Isolate Sandboxes on Vinkius. This zero-trust MCP Server architecture ensures that no financial data is cached on disk, and your API keys are never exposed to the Gemini model or Google ADK logs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript